Weak supervision target detection method and device

Abstract

The embodiment of the invention provides a weak supervision target detection method and device. The method comprises the steps of extracting image features of a to-be-detected image; wherein the to-be-detected image comprises at least one to-be-detected object; determining an initial detection result for each to-be-detected object based on the extracted image features, each initial detection result being an initial detection frame containing one to-be-detected object; based on the extracted image features, determining a salient region of each to-be-detected object; and optimizing each initialdetection result based on each salient region to obtain a target detection result for each to-be-detected object. Compared with an existing method for detecting a supervised target, a segmentation model does not need to be trained additionally, the salient region serves as the auxiliary information for optimizing the detection result, so that the training complexity of the target detection task isreduced, the salient region serves as the auxiliary information of the optimization process, errors in the optimization direction can be avoided, and the training efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a weakly supervised target detection method and device. Background technique [0002] In recent years, with the development of smart cities and camera technology, the task of object detection has been paid more and more attention. Target detection refers to the use of rectangular frames to frame different objects in the picture. [0003] As an important part of deep neural network, convolutional neural network can effectively extract image features and meet the needs of high-precision target detection. However, training a high-accuracy detection model requires a large amount of image data finely annotated in the form of bounding boxes as model supervision conditions, and a large amount of labor costs are required for labeling. With the rapid development of big data in recent years, in the face of massive visual data and higher and higher precision requirements, it is d...

AI Technical Summary

Problems solved by technology

Therefore, the training complexity of the object detection task is high

[0007] 2. The existing weakly supervised target detection will randomly select an optimization direction to calculate the error during iterative optimization training. The wrong optimization direction will make iterative training fail, so the training efficiency is low

Images